| 摘要: |
| 图像复原的目的是将原始图像从观测到的降析图像中恢复出来.提出了一种基于小波域局部高斯模型的线性图像复原算法.小波域局部高斯模型采用高斯函数刻画子带系数的局部概率分布,由于这一模型具有很好的局部自适应性,并能正确地反映图像的局部结构信息,因此算法以此作为自然图像的先验模型,把图像复原问题转化为一个约束优化问题并用共轭梯度法对其进行求解.实验结果表明,基于小波域局部高斯模型的图像复原算法较好地再现了各种边缘信息,复原出的图像在信噪比和主观视觉效果方面都有显著的提高. |
| 关键词: 图像复原 小波变换 局部高斯模型 共轭梯度法 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant Nos.60272042,10171007(国家自然科学基金) |
|
| Image Restoration Based on Wavelet-Domain Local Gaussian Model |
|
WANG Xue-Lin,HAN Hua,PENG Si-Long
|
| Abstract: |
| The aim of image restoration is to recover the original uncorrupted images from noisy, blurred ones. A linear image restoration algorithm based on a wavelet-domain local gaussian model is proposed in this paper. The wavelet-domain local gaussian model approximates the local probability distribution of the wavelet coefficients with a single gaussian function. Because the wavelet-domain local gaussian model adaptively characterizes the local statistic properties of real-world images, the algorithm presented in this paper specifies the prior distribution of the real-world image through the model and converts the restoration problem to an constrained optimization one which can be solved with the conjugate gradient method. Experimental results show that the algorithm can properly retrieve various kinds of edges, and the PNSR (peak signal to noise ratio) and subjective visual effect of the restored images are improved significantly. |
| Key words: image restoration wavelet transform local Gaussian model conjugate gradient method |
